summaryrefslogtreecommitdiff
path: root/makima/sh
Commit message (Collapse)AuthorAgeFilesLines
* Fix downloading too many modelssoryu2026-02-021-3/+21
|
* Use chatterbox TTSsoryu2026-02-011-35/+19
|
* Download vocab.json and merges.txt in container imagesoryu2026-01-301-2/+5
|
* Ensure tokenizor exists for TTS modelsoryu2026-01-291-1/+5
|
* fix: Use correct hf command for Qwen3-TTS download (#46)soryu2026-01-291-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * chore: fix unused import warnings in qwen3-tts module - Remove unused import 'IndexOp' in model.rs - Remove unused import 'DType' in speech_tokenizer.rs - Add #[allow(dead_code)] to codebook_dim field in RvqCodebook Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat: add voice loading and selection for TTS cloning Add voice reference audio loading so the TTS speak handler can perform voice cloning using reference WAV files from the voices/ directory. - Add voice.rs module: loads manifest.json and reference.wav for a given voice_id, decodes via symphonia, resamples to 24kHz for the TTS engine - Update speak.rs: resolve voice_id from the speak request (default "makima"), load reference audio, pass it to engine.generate() - Add voices/makima/README.md with instructions for obtaining reference audio (extraction from YouTube, recording, ffmpeg conversion) - Graceful fallback: if reference audio is missing, TTS proceeds without voice cloning using the model's default voice Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat: add inference cancellation support for TTS generation Add cooperative cancellation via Arc<AtomicBool> cancel flag that threads through TtsEngine::generate -> Qwen3Tts -> GenerationContext. The autoregressive loop and streaming decoder check the flag each iteration and break early when set. The speak WebSocket handler creates a per-session flag, passes it to generate, and sets it on Cancel/Stop/Close messages. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Add Qwen3-TTS model download to build process Fix TTS engine failure due to missing tokenizer by downloading Qwen3-TTS models during Docker build: - Download model.safetensors, config.json, tokenizer.json, and tokenizer_config.json from Qwen/Qwen3-TTS-12Hz-0.6B-Base - Download speech tokenizer from Qwen/Qwen3-TTS-Tokenizer-12Hz - Add QWEN3_TTS_DIR environment variable to Dockerfile - Script supports both env var override and default path Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: use correct hf command for Qwen3-TTS download Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: Add Qwen3-TTS model download to Docker build (#44)soryu2026-01-291-0/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * chore: fix unused import warnings in qwen3-tts module - Remove unused import 'IndexOp' in model.rs - Remove unused import 'DType' in speech_tokenizer.rs - Add #[allow(dead_code)] to codebook_dim field in RvqCodebook Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat: add voice loading and selection for TTS cloning Add voice reference audio loading so the TTS speak handler can perform voice cloning using reference WAV files from the voices/ directory. - Add voice.rs module: loads manifest.json and reference.wav for a given voice_id, decodes via symphonia, resamples to 24kHz for the TTS engine - Update speak.rs: resolve voice_id from the speak request (default "makima"), load reference audio, pass it to engine.generate() - Add voices/makima/README.md with instructions for obtaining reference audio (extraction from YouTube, recording, ffmpeg conversion) - Graceful fallback: if reference audio is missing, TTS proceeds without voice cloning using the model's default voice Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat: add inference cancellation support for TTS generation Add cooperative cancellation via Arc<AtomicBool> cancel flag that threads through TtsEngine::generate -> Qwen3Tts -> GenerationContext. The autoregressive loop and streaming decoder check the flag each iteration and break early when set. The speak WebSocket handler creates a per-session flag, passes it to generate, and sets it on Cancel/Stop/Close messages. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Add Qwen3-TTS model download to build process Fix TTS engine failure due to missing tokenizer by downloading Qwen3-TTS models during Docker build: - Download model.safetensors, config.json, tokenizer.json, and tokenizer_config.json from Qwen/Qwen3-TTS-12Hz-0.6B-Base - Download speech tokenizer from Qwen/Qwen3-TTS-Tokenizer-12Hz - Add QWEN3_TTS_DIR environment variable to Dockerfile - Script supports both env var override and default path Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* Add Postgres for persistence and File cabinetsoryu2025-12-234-0/+65
| | | | Migrations are local only currently, and must be run manually by setting POSTGRES_CONNECTION_URI
* Bump diarization version to 2.1 and fix downloading the tokenizersoryu2025-12-231-11/+45
|
* Use hf cli to download modelssoryu2025-12-231-2/+2
|
* Use HF to download modelssoryu2025-12-231-18/+42
|
* Create container image and move parakeet fork to vendor dirsoryu2025-12-231-0/+60
generated by cgit v1.2.3 (git 2.39.1) at 2026-05-20 23:36:44 +0000